A computer implemented method transforms an image comprised of pixels into a vectorized image specified by a plurality of polygons that can be subsequently used to aid in image processing and understanding. The pixelated image is processed to extract edge pixels that separate different colors and a constrained Delaunay triangulation of the edge pixels forms a plurality of triangles having edges that cover the pixelated image. A color for each one of the plurality of triangles is determined from the color pixels within each triangle. A filter is formed with a set of grouping rules related to features of the pixelated image and applied to the plurality of triangle edges to merge adjacent triangles consistent with the filter into polygons having a plurality of vertices. The pixelated image may be then reformed into an array of the polygons, that can be represented collectively and efficiently by standard vector image.
Legal claims defining the scope of protection, as filed with the USPTO.
1. A computer implemented method for segmenting a pixelated image formed of pixels having color values comprising: processing the image to extract edge pixels that separate different colors in said pixelated image; performing a constrained Delaunay triangulation of the edge pixels to form a plurality of triangles having edges that cover the pixelated image; determining a color for each one of the plurality of triangles from the color pixels within each triangle; defining a filter having a set of grouping rules related to features of the pixelated image; applying the filter to the plurality of triangle edges to merge adjacent triangles consistent with the filter into polygons having a plurality of vertices; and reforming the pixelated image into an array of the polygons.
2. The method of claim 1 , wherein processing the pixelated image includes processing image pixels with a Canny edge detection software program.
3. The method of claim 1 , determining the color of each one of the plurality of triangles includes using a Monte Carlo software program to sample color values for pixels within each triangle and then determining a mean value from sampled color values to form a color attributed to each triangle.
4. The method of claim 1 , wherein the grouping rules include color similarity and structural adjacency considerations.
5. The method of claim 4 , wherein the structural adjacency considerations include spacial proximity, contour continuity, and region continuity.
6. The method of claim 1 , wherein each one of the polygons is identified by a vector defined by the coordinates of the vertices and a color.
7. A computer implemented method for segmenting a pixelated image formed of pixels having color values comprising: processing the pixelated image to extract edge pixels that separate different colors in the pixelated image to form edge contours: performing a constrained Delaunay triangulation of the edge pixels to form a plurality of triangles that cover the pixelated image: defining spatial filters that define relationships between the edge contours and edges of the triangles: and applying the spatial filters to the plurality of triangles to output a plurality of polygons.
8. The method of claim 7 wherein the spatial filters include spatial proximity, spectral proximity, contour continuity, and region continuity.
9. A computer implemented method for forming a compressed image from a pixelated image formed of pixels comprising: segmenting the pixelated image into vectorized polygonal tiles; processing the pixelated image to extract edge pixels that separate different colors in the pixelated image to form edge contours: performing a constrained Delaunay triangulation of the edge pixels to form a plurality of triangles that cover the pixelated image: defining spatial filters that define relationships between the edge contours and edges of the triangles: applying the spatial filters to the plurality of triangles to output a plurality of polygons: and replacing the pixelated image with the vectorized polygonal tiles to form a compressed representation of the image.
10. The method of claim 9 , wherein the spatial filters include spatial proximity, spectral proximity, contour continuity, and region continuity.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
July 7, 2004
October 24, 2006
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.